© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 62252
    Prev
    Next
    INDEX
    Explanations

    APO, Apo, Russia, Automatic cars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ጣት
    0.45
    组织的
    0.38
    组织
    0.38
    組織
    0.38
    Hearing
    0.38
     HEARING
    0.38
    뺀
    0.37
    マネ
    0.37
     फटा
    0.37
    Thinking
    0.36
    POSITIVE LOGITS
     SA
    0.53
     APO
    0.51
     Apo
    0.49
    4
    0.49
    Sao
    0.46
     sao
    0.44
    Kir
    0.43
     Swords
    0.42
     Sword
    0.42
    apo
    0.42
    Activations Density 0.003%

    No Known Activations